SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2510.20235 · NeurIPS · 2025

Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach

Giseung Park, Youngchul Sung, Amir Leshem, Jongseong Chae, Woohyeon Byeon

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
whbyeon/ERAM-ARAM canonical 0 of 4
FunctionStatusWhere it lives
create_mlp Not yet run whbyeon/ERAM-ARAM/stable_baselines3/common/torch_layers.py
pointer only (licence: NONE) · get_code("2059f84e6efc564f")
get_actor_critic_arch Not yet run whbyeon/ERAM-ARAM/stable_baselines3/common/torch_layers.py
pointer only (licence: NONE) · get_code("f2ded9c22d608f44")
make Not yet run whbyeon/ERAM-ARAM/mo_gymnasium/utils.py
pointer only (licence: NONE) · get_code("8b6938dfd4c09200")
movingaverage Not yet run whbyeon/ERAM-ARAM/nets/4x4-Lucas/metrics/result_plot.py
pointer only (licence: NONE) · get_code("0ce0adc68bd9c4d0")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this paper, we propose a provably convergent and practical framework for multi-objective reinforcement learning with max-min criterion. From a game-theoretic perspective, we reformulate max-min multi-objective reinforcement learning as a two-player zero-sum regularized continuous game and introduce an efficient algorithm based on mirror descent. Our approach simplifies the policy update while ensuring global last-iterate convergence. We provide a comprehensive theoretical analysis on our algorithm, including iteration complexity under both exact and approximate policy evaluations, as well as sample complexity bounds. To further enhance performance, we modify the proposed algorithm with adaptive regularization. Our experiments demonstrate the convergence behavior of the proposed algorithm in tabular settings, and our implementation for deep reinforcement learning significantly outperforms previous baselines in many MORL environments.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2510.20235")
get_code_for_paper("2510.20235")
have("2510.20235")

Connect an agent — have() is free.